lidx-architecture — lidx-architecture install lidx-architecture, community, lidx-architecture install, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Modular System Agents needing comprehensive module boundary navigation and architectural planning. lidx-architecture is a skill that provides a module map for navigating and understanding the structure of a project, including entry points and module declarations.

Features

Provides a module map for navigating project structure
Includes entry point definition in main.rs
Supports CLI arg definitions using clap Parser/Subcommand
Defines module declarations in lib.rs
Helps plan architectural changes and understand module boundaries

# Core Topics

JacobSoderblom JacobSoderblom
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The lidx-architecture skill by JacobSoderblom is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for lidx-architecture install.

Ideal Agent Persona

Perfect for Modular System Agents needing comprehensive module boundary navigation and architectural planning.

Core Value

Empowers agents to design new features spanning multiple modules, understand module boundaries, and plan architectural changes using module maps and clap dispatch mechanisms.

Capabilities Granted for lidx-architecture

Designing new features across multiple modules
Understanding module boundaries before making changes
Planning architectural changes with module maps
Navigating src directory structures for efficient development

! Prerequisites & Limits

  • Requires knowledge of Rust and clap library
  • Specific to lidx-architecture and its module structure
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

lidx-architecture

Install lidx-architecture, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

lidx Architecture Navigation

When to Use This Skill

  • Designing a new feature that spans multiple modules
  • Understanding module boundaries before making changes
  • Finding where a specific piece of functionality lives
  • Planning architectural changes

Module Map

src/
  main.rs            -- Entry point, clap dispatch to serve/reindex/mcp-serve
  cli.rs             -- CLI arg definitions (clap Parser/Subcommand)
  lib.rs             -- Module declarations
  config.rs          -- Runtime config, env var overrides (LIDX_*)
  model.rs           -- All response/output types (Symbol, Edge, etc.)

  rpc.rs             -- JSONL RPC dispatch: handle_method() with ~30 methods
  mcp.rs             -- MCP stdio server: wraps rpc as single "lidx" tool

  db/
    mod.rs           -- Db struct, r2d2 pool, all SQL queries as methods
    migrations.rs    -- Schema DDL, version-gated ALTER TABLE migrations

  indexer/
    mod.rs           -- Indexer struct, orchestrates scanning + extraction + DB writes
    scan.rs          -- File discovery (ignore crate), extension-to-language mapping
    batch.rs         -- Batched DB writes for symbols/edges
    extract.rs       -- SymbolInput, EdgeInput, ExtractedFile types
    differ.rs        -- Symbol diff detection between versions
    stable_id.rs     -- Content-hash-based stable symbol identifiers
    python.rs        -- Python tree-sitter extractor
    rust.rs          -- Rust tree-sitter extractor
    javascript.rs    -- JS/TS/TSX tree-sitter extractors
    csharp.rs        -- C# tree-sitter extractor
    sql.rs           -- SQL tree-sitter extractor
    markdown.rs      -- Markdown heading extractor
    proto.rs         -- Protobuf service/method extractor + RPC edge detection
    xref.rs          -- Cross-language reference detection (C#->SQL, C#->Python)
    channel.rs       -- CHANNEL_PUBLISH/SUBSCRIBE detection (message bus)
    http.rs          -- HTTP_CALL/HTTP_ROUTE detection
    test_detection.rs -- Identifies test files and test functions

  impact/
    mod.rs           -- Impact analysis module root
    orchestrator.rs  -- Multi-layer impact orchestration
    layers/          -- Impact layers (direct, test, historical)
    types.rs         -- Impact-specific types
    confidence.rs    -- Confidence scoring for impact edges
    config.rs        -- Impact analysis configuration

  search.rs          -- Text search: ripgrep subprocess + result parsing
  subgraph.rs        -- Multi-root BFS expansion over the symbol graph
  gather_context.rs  -- Budget-aware context assembly (byte/node/depth limits)
  watch.rs           -- File watching (notify crate), debounce, fallback polling
  git_mining.rs      -- Git log mining for co-change history
  metrics.rs         -- File and symbol metrics (LOC, complexity, duplication)
  diagnostics.rs     -- Diagnostic ingestion (SARIF, inline)
  repo_map.rs        -- Repository map generation
  util.rs            -- Shared utilities

Data Flow

Indexing: filesystem -> scan.rs (discover files) -> language extractor (tree-sitter AST -> SymbolInput/EdgeInput) -> post-passes (xref, channel, http) -> batch.rs (bulk insert) -> SQLite

Querying: stdin -> mcp.rs/rpc.rs (parse request) -> handle_method() (dispatch) -> Db methods (SQL queries) -> response JSON with next_hops -> stdout

Watch loop: notify events -> debounce -> batch of changed paths -> Indexer::sync_paths() -> re-extract + diff + update DB


Key Types

  • Symbol / SymbolCompact -- full and abbreviated symbol representations
  • Edge -- graph edge with kind, source/target, evidence, confidence
  • ExtractedFile -- output of a language extractor (symbols + edges + metrics)
  • Indexer -- owns all extractors, DB handle, scan options
  • Db -- SQLite pool + write mutex, all query methods

Finding Things

  • RPC method implementation: search for "method_name" => in src/rpc.rs
  • DB query: search for the method name in src/db/mod.rs
  • Edge kind usage: grep for the kind string (e.g., "CHANNEL_PUBLISH")
  • Response types: src/model.rs
  • Language-specific extraction: src/indexer/{language}.rs
  • Tests: tests/{feature}.rs, fixtures in tests/fixtures/

Quick Reference

RPC dispatch: src/rpc.rs -> handle_method() DB queries: src/db/mod.rs Migrations: src/db/migrations.rs Language extractors: src/indexer/{lang}.rs Response types: src/model.rs Tests: tests/, fixtures in tests/fixtures/

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is lidx-architecture?

Perfect for Modular System Agents needing comprehensive module boundary navigation and architectural planning. lidx-architecture is a skill that provides a module map for navigating and understanding the structure of a project, including entry points and module declarations.

How do I install lidx-architecture?

Run the command: npx killer-skills add JacobSoderblom/lidx/lidx-architecture. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for lidx-architecture?

Key use cases include: Designing new features across multiple modules, Understanding module boundaries before making changes, Planning architectural changes with module maps, Navigating src directory structures for efficient development.

Which IDEs are compatible with lidx-architecture?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for lidx-architecture?

Requires knowledge of Rust and clap library. Specific to lidx-architecture and its module structure.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add JacobSoderblom/lidx/lidx-architecture. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use lidx-architecture immediately in the current project.

Related Skills

Looking for an alternative to lidx-architecture or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI